Just Kwit: Mobile Intervention for Tobacco Cessation: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Just Kwit: Mobile Intervention for Tobacco Cessation (NCT03538678), a randomized na study. The primary outcome is Feasibility - Helpfulness and Ease of Use of the Intervention Smartphone App.

2. Clinical Question

The trial is listed as randomized, with a parallel-group design and no masking. Its two arms are the Kwit app and standard of care. The registry identifies the primary endpoint as feasibility, assessed through a follow-up survey. Participants were asked to rate helpfulness, ease of use, and frustration, and to describe what they found helpful or not helpful about the app.

The survey was to be administered one month after discharge by email, phone, or in person, according to each participant’s preference. The primary endpoint applies only to the experimental arm. This scope matters: the stated primary question concerns participants’ experience of the app, not whether app use produced a better cessation outcome than standard of care. The record lists cessation-related secondary outcomes, including point-prevalence abstinence, cigarettes smoked, days smoked, and confidence, but reports no analyses for them.

3. Trial Design

The registry describes Just Kwit as a randomized, parallel-group study with no masking. Enrollment was 40. Participants were assigned to the Kwit app or standard of care; the safety record lists 20 participants at risk in each group. The study is marked completed, and its phase is listed as not applicable.

The intervention was use of the Kwit smartphone app. The registry says its main features include motivational messages, displaying money saved, and a way to log cravings. The comparator is described as patient-initiated follow-up after discharge. The record does not specify further details about standard-of-care services or explain how the app was introduced or supported.

The listed primary endpoint concerns feasibility, with assessment one month after discharge. A follow-up survey was to be administered through a mode chosen according to participant preference: email, phone, or in-person contact. The questions asked participants to rate the app’s helpfulness, ease of use, and frustration, and included open-ended questions about helpful and unhelpful aspects. The primary endpoint is applicable only to the experimental arm.

The registry lists secondary outcomes concerning point-prevalence abstinence, cigarettes smoked, days smoked, and confidence. It records six outcome measures overall, but records no analyses. The detailed eligibility criteria, allocation procedure, and participant characteristics are not reported in the registry record. Nor does the record state whether participants were followed for outcomes beyond the one-month feasibility survey or how any such follow-up was conducted.

The registry gives the study start as 2018-06-11 and primary completion as 2019-12-29. The sponsor is the University of Pittsburgh. A completed status indicates the registry’s stated study status; it does not itself establish that all outcomes were analyzed or that results were reported.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Only applicable for experimental arm

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Feasibility - Helpfulness and Ease of Use of the Intervention Smartphone App, measured over 1-month.

The primary endpoint is labeled “Feasibility - Helpfulness and Ease of Use of the Intervention Smartphone App.” It concerns participants’ assessments of the app, collected at one month after discharge. The planned survey asks how helpful the app was, whether it was easy to use, and whether it was frustrating. It also asks what, if anything, participants found helpful or not helpful.

The registry describes the measure as a count of participants and says descriptive statistics will be used to assess feasibility. The survey responses include ordered verbal rating choices and open-ended responses. The endpoint is applicable only to the experimental arm; it is therefore an assessment of experience with the app, rather than an outcome that directly compares app participants with the standard-of-care group.

Feasibility measures are used to characterize whether an intervention can be used and how participants experience it. As a general statistical point, such measures can help describe practical acceptability and identify difficulties that might need attention in later evaluation. They do not, by themselves, estimate whether an intervention changes smoking behavior or cessation outcomes. The registry record does not report the survey responses, the number of participants who completed the survey, or a numerical feasibility result. It also does not report how the verbal response categories or written answers were to be summarized beyond the stated use of descriptive statistics.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a randomized parallel-group design without masking. Randomization is a method for assigning participants to study groups by chance. In general, it aims to reduce systematic differences between groups at the time of assignment, so that a between-group outcome comparison can be interpreted more fairly. It does not guarantee that groups will be identical, and it cannot resolve problems caused by incomplete follow-up or unreported outcome data. The record does not describe the randomization sequence, how allocation was concealed, or whether any restrictions were used.

What does the primary endpoint measure?

The primary endpoint is feasibility as assessed through participant ratings and comments about the Kwit app. The planned questions cover helpfulness, ease of use, frustration, and what participants found helpful or not helpful. The registry says descriptive statistics will be used. Descriptive statistics organize and characterize observed responses; they do not, by themselves, test whether the app changed a clinical outcome or establish a causal effect. The endpoint is restricted to the experimental arm, so it is not described as a randomized comparison between app and standard-of-care participants.

The response choices include ordered verbal categories, while the open-ended questions invite written answers. As a general statistical consideration, ordered categories retain a ranking but do not necessarily represent equal distances between responses. The registry does not report a planned scoring rule, a method for combining answers, or a qualitative coding approach for written comments. It also does not report how the intended descriptive summaries would be presented.

What does the design say about comparison?

The study includes an app arm and a standard-of-care arm. A randomized comparison could be used to estimate a difference in an outcome if comparable outcome data were collected and analyzed for both groups. Here, the stated primary endpoint applies only to app participants, and the registry lists cessation measures as secondary outcomes. The record reports no analyses, so it contains no estimated between-group contrast for the named cessation outcomes. Design features alone cannot supply such an estimate.

For a general explanation, an effect estimate describes the observed contrast or quantity of interest, while a confidence interval describes the statistical uncertainty around an estimate under the assumptions of the analysis. A narrower interval generally indicates greater precision, whereas a wider interval indicates more uncertainty. No confidence interval or outcome estimate is reported in this registry record, so precision cannot be assessed for the primary or secondary outcomes.

What can be said about planning assumptions?

The record includes a sample-size planning illustration framework, explicitly distinguished from the trial’s own design. Its stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect defined as a stated fraction of the observed effect. It also distinguishes the reporting unit for time-to-event illustrations from other illustrations. These are planning assumptions, not evidence that the trial was designed around those assumptions or that its observed results achieved a particular level of power.

General statistical context: planning calculations describe what sample size might be needed under specified assumptions. They depend on the assumed effect, outcome variability or event frequency, analysis method, and desired operating characteristics. If the assumed effect differs from a later observed effect, the resulting illustration can differ as well. Such calculations are not “observed power” and do not replace an estimate with an uncertainty interval. The registry does not report the trial’s own sample-size justification, and no outcome estimates are available in the posted record for interpreting the planning illustration.

Why is dispersion relevant?

General statistical context: for count outcomes, a model may need to account for how variable the counts are. Over-dispersion occurs when count variability is greater than a simple model assumes. Ignoring it can make uncertainty appear smaller than it is. Whether over-dispersion is relevant depends on the outcome data and chosen model. The record does not report an analyzed count outcome, a fitted model, or a modeling plan, so no claim about over-dispersion or model choice can be made for this study.

Similarly, statistical tests and confidence intervals depend on the analysis population, outcome definition, and assumptions used. Those details are not reported for any completed outcome analysis. Since the registry records zero analyses, the available information supports explaining the planned endpoint and design, but not reconstructing inferential results.

10. Multiplicity, Missing Data and Analysis Populations

The registry names a feasibility primary endpoint and several cessation-related secondary outcomes. The primary assessment includes multiple questions and response types, while the registry also lists point-prevalence abstinence, cigarettes smoked, days smoked, and confidence as secondary outcomes. The record does not report a statistical analysis plan addressing multiplicity, such as whether any outcomes or comparisons would be prioritized or whether adjustment for multiple testing was planned. Without reported analyses, there are no test results to interpret in light of multiplicity.

The record does not report missing-data procedures. It does not state how unanswered survey questions, participants lost to follow-up, or unavailable secondary outcome measurements would be handled. It also does not report survey completion, response rates, or reasons for missingness. As a general statistical point, missingness can affect both the number of observations contributing to an analysis and the interpretation of its results. The consequences depend on why data are missing and on the analysis approach; those details cannot be inferred from the registry description.

The analysis populations are not reported in the registry record. In particular, the record does not say which participants would be included in analyses of the randomized comparison, how participants who did not use the app would be treated analytically, or how the one-arm feasibility responses would be summarized if participants did not respond. No outcome analyses are listed. The distinction between randomized assignment, participation in the app, survey response, and inclusion in an analysis is therefore not resolved by the posted record.

These omissions do not show that the study failed to collect data or that analyses were not conducted outside the registry; they mean only that the registry record does not report them. A complete interpretation would require the relevant analysis methods, outcome counts or summaries, and information on missing observations. None of those results are posted in the record.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry safety record lists 20 participants at risk in the Kwit App group and 20 in the Standard of Care group. For each group it records zero serious adverse events, zero other adverse events, and zero deaths. These entries describe the safety counts recorded in the registry.

A zero count means no events of that recorded type appear in the registry figures; it does not provide detail about how events were solicited, defined, reviewed, or followed over time. The record does not report a list of serious-event terms, and it does not provide additional safety analyses or uncertainty estimates. It also does not describe whether event ascertainment was identical between groups or whether any participants had incomplete safety follow-up.

As a general statistical point, absence of recorded events is not the same as proof that an event cannot occur. Safety counts must be interpreted in relation to the scope and completeness of monitoring, the population observed, and the duration of observation. Those details are not reported in the registry record. The figures should therefore be read narrowly as the posted event counts, not as a complete characterization of safety or a comparison establishing a safety difference between groups.

12. What the Result Does, and Does Not, Mean

The record describes a randomized evaluation of a smartphone app intended to support tobacco cessation, with standard of care as the comparator. Its primary endpoint concerns feasibility: app participants were to rate helpfulness, ease of use, and frustration and describe helpful or unhelpful features. The planned follow-up survey was one month after discharge, and the stated endpoint applies only to the app arm.

The posted record does not include results for those survey questions. It also does not report analyses of the named secondary outcomes concerning abstinence, cigarettes smoked, days smoked, or confidence. Thus, there is no reported effect estimate, no measure of statistical uncertainty, and no basis in this record for describing the direction or magnitude of a cessation outcome. The trial’s randomized design is relevant to how a comparative evaluation could be conducted, but it cannot substitute for reported outcome data.

The record’s completed status and enrollment count describe the trial record, not the findings. Likewise, the absence of recorded adverse events is a statement about the safety counts listed, not a general claim that harms are impossible or that all safety questions have been answered. Interpretation of those counts is limited by the lack of detail on monitoring and follow-up.

General statistical interpretation distinguishes the question a study set out to address from the result it actually reports. A feasibility survey can describe participant experience, while cessation outcomes address smoking behavior. Evidence for one does not automatically answer the other. The registry record supports explaining the planned feasibility assessment, the group structure, and the reported safety counts; it does not support a conclusion about whether the app changed cessation outcomes or how precisely such a change might be estimated.

The appropriate reading is therefore limited: the record documents a completed randomized study and its planned endpoint, but no analyzed efficacy or feasibility results are posted. Any interpretation beyond those details would require outcome data and analysis information not reported in the registry record.

13. Why This Trial Matters Statistically

This trial is statistically notable for the distinction between a feasibility endpoint and a clinical outcome. The stated primary question is about how app participants experienced the intervention, including helpfulness, ease of use, frustration, and written comments. Cessation-related outcomes appear as secondary outcomes. These outcomes address different questions, and findings about usability would not automatically establish a change in abstinence or smoking behavior.

The study also illustrates why a randomized design and reported results are separate parts of an evidence assessment. Random assignment can support a fair comparison when outcomes are measured and analyzed appropriately. But this registry record lists zero analyses, so it does not provide the outcome estimates needed to evaluate a comparative effect. A design description cannot establish the direction, size, or precision of an effect on its own.

Another point is that the primary feasibility measure applies only to the experimental arm. That makes it an account of app participants’ reported experience, rather than a direct app-versus-standard-of-care contrast. The registry’s description of multiple rating questions and open-ended responses also highlights that an endpoint may have several components. Without the results and the planned approach to summarizing them, readers cannot know how those components were ultimately interpreted.

The record gives a sample-size illustration framework but distinguishes it from the trial’s own design. This distinction is important in general: planning calculations rest on assumptions, and they should not be treated as evidence that an observed effect was detected or that a study had a particular observed power. The registry does not report the trial’s own sample-size justification.

Finally, the study underscores the value of complete registry reporting. Outcome estimates, uncertainty intervals, analysis populations, missing-data handling, and analysis methods are necessary to understand what the collected data show. Their absence does not determine what the results would be; it limits what can be concluded from this record.

14. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most important limitation for interpretation is that the registry reports no analyses. It contains no numerical results for the primary feasibility endpoint or the secondary cessation outcomes. Accordingly, the size and precision of any observed outcome cannot be assessed from the record.

The primary endpoint is applicable only to the app arm, and it consists of multiple ratings and open-ended questions. The registry does not report how these answers were summarized, whether a composite score was planned, or how written responses were to be categorized. It also does not report how many participants completed the follow-up survey or whether responses were missing.

The record gives limited detail about the comparator, describing it as patient-initiated follow-up after discharge. Additional information on the standard-of-care content, eligibility criteria, participant characteristics, randomization procedures, and allocation concealment is not reported in the registry record. These omissions restrict assessment of the context and implementation of the comparison.

Analysis populations, missing-data methods, multiplicity procedures, and the statistical plan are not reported. The record also does not provide outcome definitions or analysis details for the listed secondary outcomes. Without those details and the underlying results, readers cannot evaluate the robustness of estimates or determine how the analyses addressed incomplete data and multiple outcomes.

The safety figures are limited to the counts recorded in the registry; the record does not provide further detail on event ascertainment, follow-up completeness, or safety methods. Finally, the sample-size assumptions are described as a planning illustration rather than the trial’s design justification. They should not be used to infer the study’s planned power or the strength of any unreported result.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Just Kwit: Mobile Intervention for Tobacco Cessation — NCT03538678.
• Registry record last updated 2021-02-18; status last verified 2021-02.
• Results first posted 2021-02-18.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

Just Kwit is listed as a completed randomized, parallel-group study with no masking and enrollment of 40. The sponsor is the University of Pittsburgh. The intervention was use of the Kwit smartphone app, whose stated features include motivational messages, displaying money saved, and logging cravings. The comparator was patient-initiated follow-up after discharge.

The primary endpoint concerns app feasibility, assessed through participant ratings and comments one month after discharge. It applies only to the app arm. The record lists cessation-related secondary outcomes, including point-prevalence abstinence, cigarettes smoked, days smoked, and confidence, but reports zero analyses and no outcome estimates.

The safety record lists 20 participants at risk in each group, with zero serious adverse events, zero other adverse events, and zero deaths recorded in either group. The registry does not report analysis populations, missing-data procedures, or the study’s own sample-size justification. The posted information supports a description of the design and planned endpoint, but not conclusions about cessation outcomes or the precision of an effect.